This study examines temporal patterns of software systems defects using the Autoregressive Integrated Moving Average (ARIMA) approach. Defect reports from ten software application projects are analyzed;five of these p...This study examines temporal patterns of software systems defects using the Autoregressive Integrated Moving Average (ARIMA) approach. Defect reports from ten software application projects are analyzed;five of these projects are open source and five are closed source from two software vendors. Across all sampled projects, the ARIMA time series modeling technique provides accurate estimates of reported defects during software maintenance, with organizationally dependent parameterization. In contrast to causal models that require extraction of source-code level metrics, this approach is based on readily available defect report data and is less computation intensive. This approach can be used to improve software maintenance and evolution resource allocation decisions and to identify outlier projects—that is, to provide evidence of unexpected defect reporting patterns that may indicate troubled projects.展开更多
This paper proposes an evolutionary optimized recurrent neural network for inspection of open/short defects on thin film transistor (TFT) lines of flat panel displays (FPD). The inspection is performed on digitized wa...This paper proposes an evolutionary optimized recurrent neural network for inspection of open/short defects on thin film transistor (TFT) lines of flat panel displays (FPD). The inspection is performed on digitized waveform data of voltage signals that are captured by a capacitor based non-contact sensor through scanning over TFT lines on the surface of mother glass of FPD. Irregular patterns on the waveform, sudden deep falls (open circuits) or sharp rises (short circuits), are classified and detected by employing the optimized recurrent neural network. The topology parameters of the recurrent neural network are optimized by a multiobjective evolutionary optimization process using a selected training data set. This method is an extension to our previous work, which utilized a feed-forward neural network, to address the drawbacks in it. Experimental results show that this method can detect defects on more realistic and noisy data than both of the previous method and the conventional threshold based method.展开更多
文摘This study examines temporal patterns of software systems defects using the Autoregressive Integrated Moving Average (ARIMA) approach. Defect reports from ten software application projects are analyzed;five of these projects are open source and five are closed source from two software vendors. Across all sampled projects, the ARIMA time series modeling technique provides accurate estimates of reported defects during software maintenance, with organizationally dependent parameterization. In contrast to causal models that require extraction of source-code level metrics, this approach is based on readily available defect report data and is less computation intensive. This approach can be used to improve software maintenance and evolution resource allocation decisions and to identify outlier projects—that is, to provide evidence of unexpected defect reporting patterns that may indicate troubled projects.
文摘This paper proposes an evolutionary optimized recurrent neural network for inspection of open/short defects on thin film transistor (TFT) lines of flat panel displays (FPD). The inspection is performed on digitized waveform data of voltage signals that are captured by a capacitor based non-contact sensor through scanning over TFT lines on the surface of mother glass of FPD. Irregular patterns on the waveform, sudden deep falls (open circuits) or sharp rises (short circuits), are classified and detected by employing the optimized recurrent neural network. The topology parameters of the recurrent neural network are optimized by a multiobjective evolutionary optimization process using a selected training data set. This method is an extension to our previous work, which utilized a feed-forward neural network, to address the drawbacks in it. Experimental results show that this method can detect defects on more realistic and noisy data than both of the previous method and the conventional threshold based method.
